© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8782
    Prev
    Next
    INDEX
    Explanations

    phrases that initiate questions or seek clarification about actions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.91
    adpleegd
    -0.66
     дописавши
    -0.61
     Audiodateien
    -0.59
     незавершена
    -0.57
    DoubleQuotes
    -0.56
     виправивши
    -0.56
    InputTagHelper
    -0.56
     ['./
    -0.55
     חיצוניים
    -0.55
    POSITIVE LOGITS
     kuin
    0.57
     kanssa
    0.55
    okości
    0.55
    Legenda
    0.55
    glTexCoord
    0.53
    Geschiedenis
    0.48
     téc
    0.48
    msgSender
    0.47
    друг
    0.47
    onaceous
    0.47
    Activations Density 0.171%

    No Known Activations